Recent advances and challenges in task-oriented dialog systems

Due to the significance and value in human-computer interaction and natural language processing, task-oriented dialog systems are attracting more and more attention in both academic and industrial communities. In this paper, we survey recent advances and challenges in task-oriented dialog systems. W...

Full description

Saved in:
Bibliographic Details
Published in:Science China. Technological sciences 2020-10, Vol.63 (10), p.2011-2027
Main Authors: Zhang, Zheng, Takanobu, Ryuichi, Zhu, Qi, Huang, MinLie, Zhu, XiaoYan
Format: Article
Language:English
Subjects:
Engineering
Modelling
Natural language processing
Review
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Due to the significance and value in human-computer interaction and natural language processing, task-oriented dialog systems are attracting more and more attention in both academic and industrial communities. In this paper, we survey recent advances and challenges in task-oriented dialog systems. We also discuss three critical topics for task-oriented dialog systems: (1) improving data efficiency to facilitate dialog modeling in low-resource settings, (2) modeling multi-turn dynamics for dialog policy learning to achieve better task-completion performance, and (3) integrating domain ontology knowledge into the dialog model. Besides, we review the recent progresses in dialog evaluation and some widely-used corpora. We believe that this survey, though incomplete, can shed a light on future research in task-oriented dialog systems.
ISSN:1674-7321
1869-1900
DOI:10.1007/s11431-020-1692-3